Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/viibridges/crossnet
Cross-view Supervised Learning
https://github.com/viibridges/crossnet
Last synced: 3 months ago
JSON representation
Cross-view Supervised Learning
- Host: GitHub
- URL: https://github.com/viibridges/crossnet
- Owner: viibridges
- Created: 2016-11-15T13:38:58.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2018-10-01T15:55:24.000Z (about 6 years ago)
- Last Synced: 2024-07-25T13:48:54.169Z (4 months ago)
- Language: Python
- Size: 796 KB
- Stars: 47
- Watchers: 2
- Forks: 14
- Open Issues: 13
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
Crossnet, a cross-view supervised learning solution
========This code is a tensorflow implementation of this paper, [Predicting Ground-Level Scene Layout from Aerial Imagery](http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhai_Predicting_Ground-Level_Scene_CVPR_2017_paper.pdf).
And you are welcome to visit our [Project Page](http://cs.uky.edu/~ted/research/crossview/)
Dependencies
------------
* Tensorflow r1.1 or higher [Installation Page](https://www.tensorflow.org/versions/r1.1/install/).Running
------------
Training:
```bash
$ python main.py
```Deploying:
```bash
$ python main.py --is_training=False
```
Data
------------
This repo only contains some example data for training, the whole dataset can be found in [this link](https://drive.google.com/open?id=0BzvmHzyo_zCAX3I4VG1mWnhmcGc).
You would have to edit the dataset path in main.py in order to use it.Note
------------
We plan to release evaluation code soon.